Aleix Conchillo Flaqué
0d6eee705f
Merge pull request #190 from TomTom101/TomTom101/langchain
...
Langchain service
2024-06-01 04:21:12 +08:00
Aleix Conchillo Flaqué
42f772beed
examples: some function calling examples cleanup
2024-05-31 11:36:04 -07:00
TomTom101
4b39efeee3
fix(langchain): try/catch langchain import in service; Only langchain is installed with the [langchain] extra ( #190 )
2024-05-31 10:19:27 +02:00
chadbailey59
4c3d19cc8b
Function calling ( #175 )
...
* added function calling code back
* removed old llm_context file
* added integration testing for openai
* added function calling example
* added function callbacks
* added function start callback
* fixup
* fixup
* added different return type support for function calling
* intake example working
* added frame loggers
* cleanup
* fixup
* Update openai.py
* removed function call frame types
* fixup
* re-added example
* renumbered wake phrase
* fixup for autopep8
* remove unused imports
2024-05-30 12:25:39 -05:00
TomTom101
b19243ab75
fix: corrected hint to install Langchain libs
2024-05-30 10:53:42 +02:00
Kwindla Hultman Kramer
920745345a
cartesia tts support
2024-05-29 23:35:35 -07:00
TomTom101
335990c145
wip: hint to install langchain_community
2024-05-30 03:15:14 +02:00
TomTom101
6d24e836b0
wip: Example using LC message history
2024-05-30 03:15:14 +02:00
TomTom101
278a2fed56
wip: First stab at langchain support
...
Is this a service or processor?
How to deal with conversation history? LC has sophisticated means of this, but might get in the way of `LLMResponseAggregator`
2024-05-30 03:15:14 +02:00
Aleix Conchillo Flaqué
6d6d9bea5a
introduce PipelineParams
2024-05-28 17:14:14 -07:00
Kwindla Hultman Kramer
3685c19b2d
moving Deepgram TTS base_url from beta to prod
2024-05-28 15:59:26 -07:00
Aleix Conchillo Flaqué
afea6f38f6
examples: no need to define tts twice
2024-05-24 09:23:00 -07:00
Aleix Conchillo Flaqué
c45d428551
services(google): make api_key argument mandatory
2024-05-24 09:23:00 -07:00
Kwindla Hultman Kramer
681250f114
add new response frame types and vision support for anthropic
2024-05-22 21:12:30 -07:00
Aleix Conchillo Flaqué
acd2d55b84
examples(14): remove commented code
2024-05-22 19:05:18 -07:00
Aleix Conchillo Flaqué
0e5711e62d
examples: update 10-wake-work.py to use WakeCheckFilter
2024-05-22 15:44:44 -07:00
Aleix Conchillo Flaqué
0ddfa3de5b
move WakeCheckFilter to processors/filters
2024-05-22 15:44:43 -07:00
Kwindla Hultman Kramer
2c32cc2f27
improved wake word filter
2024-05-22 15:44:43 -07:00
Kwindla Hultman Kramer
66377954cb
fix up openai vision and gemini implementation
2024-05-19 12:33:57 -07:00
Kwindla Hultman Kramer
b337e984b3
Initial commit of Google Gemini LLM service.
...
Gemini text input works. We translate from OpenAILLMContext format
on the fly in the GoogleLLMService implementation. This commit also
implements image input (vision) in both the GoogleLLMService and in
the OpenAILLMService. Image input is a hack and needs to be revisited.
OpenAI expects images to be uploaded as base64-encoded JPEGs. Google
does not require the base64 encoding. Other than for images, we use
the OpenAI format as our standard, but base64-encoding the images
and then unencoding them in the GoogleLLMService feels wasteful.
2024-05-19 10:35:20 -07:00
Aleix Conchillo Flaqué
c0d5054798
examples: some prompt tweaking
2024-05-19 09:41:36 -07:00
Aleix Conchillo Flaqué
810dc30d3d
examples: fix examples to use LLMFullResponseEndFrame
2024-05-19 09:39:34 -07:00
Aleix Conchillo Flaqué
435fffe1b0
add LLMFullResponseStartFrame/LLMFullResponseEndFrame
2024-05-18 09:49:38 -07:00
Aleix Conchillo Flaqué
2b8f1c4cda
services(openai): send LLMResponseStartFrame for each completion
2024-05-17 17:47:33 -07:00
Aleix Conchillo Flaqué
c77db79447
examples: pipelines readability and add LLM assistants after transport
2024-05-17 14:52:51 -07:00
Aleix Conchillo Flaqué
d66a795413
examples: use SileroVADAnalyzer instead of SileroVAD
2024-05-17 14:18:55 -07:00
Aleix Conchillo Flaqué
a5d246ec0c
vad: use exponential smoothing to avoid sudden changes
2024-05-17 13:53:33 -07:00
Aleix Conchillo Flaqué
f432e2b17e
transports: allow adding a vad analyzer to BaseInputTransport
2024-05-17 13:50:48 -07:00
Aleix Conchillo Flaqué
8c877d7d8e
examples: update 07-interruptible
2024-05-17 13:50:48 -07:00
Aleix Conchillo Flaqué
8965ff27ec
examples: use DEBUG in 09-mirror.py
2024-05-14 19:25:31 -07:00
Aleix Conchillo Flaqué
f6257a86d3
examples: re-enable audio in 09-mirror.py
2024-05-14 19:23:35 -07:00
Aleix Conchillo Flaqué
bd04ea8aca
examples: simplify 09-mirror.py
2024-05-14 19:07:19 -07:00
Aleix Conchillo Flaqué
b254525d3c
go back to using @dataclass since they can be inspected
2024-05-12 22:35:43 -07:00
Aleix Conchillo Flaqué
bfd583211c
examples: use LocalAudioTransport
2024-05-12 10:07:54 -07:00
Aleix Conchillo Flaqué
b026915d19
initial commit for new pipecat architecture
2024-05-12 10:07:25 -07:00
Aleix Conchillo Flaqué
7b49c9ade3
services: FalImageGenService now uses fal-client library
2024-04-11 14:09:01 -07:00
Aleix Conchillo Flaqué
1e83a405c0
Merge pull request #117 from daily-co/llm-use-aggregator-pass-through-fix
...
aggregators: fix LLMUserResponseAggregator passs-through
2024-04-12 04:24:56 +08:00
Aleix Conchillo Flaqué
7336866a1c
examples: rely on new daily default transcription settings
2024-04-11 11:22:58 -07:00
Aleix Conchillo Flaqué
e288aa047b
examples: use LLMUserResponseAggregator with VAD
2024-04-11 08:10:56 -07:00
Aleix Conchillo Flaqué
130e418800
moondream: allow passing use_cpu
2024-04-10 17:43:44 -07:00
Aleix Conchillo Flaqué
1a0a66e503
Merge pull request #114 from daily-co/jpt/fal-updates
...
Updated Fal.ai service to take a params model and allow for model string param
2024-04-11 00:47:33 +08:00
Aleix Conchillo Flaqué
e22babbae2
examples: update with new FalImageGenService parameters
2024-04-10 09:45:08 -07:00
Aleix Conchillo Flaqué
3c20f9153d
added VisionImageFrame and VisionImageFrameAggregator
2024-04-10 09:19:34 -07:00
Aleix Conchillo Flaqué
34a6c5691b
examples: added 12-describe-video
2024-04-09 22:36:35 -07:00
Aleix Conchillo Flaqué
9fcbb36997
examples: add 14a-local-render-remote-participant
2024-04-09 19:46:10 -07:00
Aleix Conchillo Flaqué
8d73cdb2ee
Merge pull request #111 from daily-co/user-transcription-aggregator
...
pipeline: add UserTranscriptionAggregator
2024-04-09 23:34:52 +08:00
Aleix Conchillo Flaqué
97b923e37e
llm user and assistant aggregator renames
2024-04-09 08:31:48 -07:00
Aleix Conchillo Flaqué
57aabea0a3
examples: added 14-render-remote-participant
2024-04-09 08:01:14 -07:00
Aleix Conchillo Flaqué
319b8e7816
updated ImageFrame and added URLImageFrame and UserImageFrame
2024-04-08 23:23:33 -07:00
Aleix Conchillo Flaqué
96950ca6df
daily: on_first_other_participant_joined now gets the participant
2024-04-08 23:23:33 -07:00
